Health Life

Discovery of aggressive cancer cell types made possible with machine learning techniques

Credit: Jonathan Irish

By applying unsupervised and automated machine learning techniques to the analysis of millions of cancer cells, Rebecca Ihrie and Jonathan Irish, both associate professors of cell and developmental biology, have identified new cancer cell types in brain tumors. Machine learning is a series of computer algorithms that can identify patterns within enormous quantities of data and get ‘smarter’ with more experience. This finding holds the promise of enabling researchers to better understand and target these cell types for research and therapeutics for glioblastoma—an aggressive brain tumor with high mortality—as well as the broader applicability of machine learning to cancer research.

With their collaborators, Ihrie and Irish developed Risk Assessment Population IDentification (RAPID), an open-source algorithm that revealed coordinated patterns of protein expression and modification associated with survival outcomes.

The article, “Unsupervised machine learning reveals risk stratifying glioblastoma tumor cells” was published online in the journal eLife on June 23. RAPID code and examples are available on the cytolab Github page.

For the past decade, the has been working to leverage machine learning’s ability to absorb and analyze more data for cell research than the alone can process. “Without any human oversight, RAPID combed through 2 million tumor cells—with at least 4,710 glioblastoma cells from each patient—from 28 glioblastomas, flagging the most unusual cells and patterns for us to look into,” said Ihrie. “We’re able to find the needles in the haystack without searching the entire haystack. This technology lets us devote our attention to better understanding the most dangerous and to get closer to ultimately curing brain cancer.”

Fed into RAPID were data on cellular proteins that govern the identity and function of neural stem cells and other brain cells. The data type used is called single-cell mass

Health article

Methylmalonic Acid (MMA) Test: MedlinePlus Medical Test

What happens during an MMA test?

MMA levels may be checked in blood or urine.

During a blood test, a health care professional will take a blood sample from a vein in your arm, using a small needle. After the needle is inserted, a small amount of blood will be collected into a test tube or vial. You may feel a little sting when the needle goes in or out. This usually takes less than five minutes.

During a newborn screening, a health care provider will clean your baby’s heel with alcohol and poke the heel with a small needle. The provider will collect a few drops of blood and put a bandage on the site.

MMA urine testing may be ordered as a 24-hour urine sample test or a random urine test.

For a 24-hour urine sample test, you’ll need to collect all urine passed in a 24-hour period. Your health care provider or a laboratory professional will give a container to collect your urine and instructions on how to collect and store your samples. A 24-hour urine sample test generally includes the following steps:

  • Empty your bladder in the morning and flush that urine away. Record the time.
  • For the next 24 hours, save all your urine passed in the container provided.
  • Store your urine container in the refrigerator or a cooler with ice.
  • Return the sample container to your health care provider’s office or the laboratory as instructed.

For a random urine test, your sample of urine may be collected any time of the day.

Source link